Credit: Unspash
Powering AI Efficiency: Nvidia, Dell, and Qualcomm Lead the Pack in Latest Benchmark Test
The latest benchmark test for artificial intelligence showcased the efforts of Nvidia, Dell, Qualcomm, and a group of startups to improve the efficiency of running AI programs while conserving power. The rising compute demand for running AI programs that are growing in size, such as OpenAI’s ChatGPT and GPT-4, has become a pressing issue.
The benchmark test was presented by MLCommons, the consortium that runs the MLPerf tests. Leading vendors such as Nvidia, Dell, Qualcomm, and Supermicro submitted computer systems with various configurations of chips to see which systems took the top marks.
They competed to deliver the most questions that could be answered per second, the least time to answer (latency), or the least amount of power consumed (energy efficiency).
In addition to the leading vendors, several startups including Neural Magic, xFusion, cTuning, Nettrix, Neuchips, Moffett, and Krai also participated in the benchmark test.
As the dominant supplier of GPUs used to run AI, Nvidia picked up many honors for performance on most of the tests.
In five out of the six different benchmark tasks, Nvidia’s system running on two Intel Xeon processors and eight of Nvidia’s “Hopper” GPU chips took the top spot, including running the Google BERT language model, a precursor to ChatGPT. In one of the six tasks, a Dell system using an almost identical configuration of Intel and Nvidia chips took the top spot.
Nvidia, Dell, and Qualcomm speed up AI results in latest benchmark tests https://t.co/tVtLEd1VK5 via @ZDNET & @TiernanRayTech #TechTrends
— PC-Canada.com (@PCCanadacom) April 6, 2023
These results are significant for companies like OpenAI, pushing the boundaries of AI and deep learning with their programs. The size of these programs continues to grow, making it increasingly challenging to run them efficiently.
Vendors like Nvidia, Dell, and Qualcomm providing powerful, energy-efficient systems could help manage the compute demand for running AI programs more effectively.
The latest benchmark test for AI is a crucial milestone in advancing AI and deep learning. It showcases the capabilities of leading vendors and startups to deliver innovative solutions that address the challenges of running increasingly large and complex AI programs.
With further research and development, we can expect even more powerful and energy-efficient systems that will help propel the AI industry forward.
